# CAR-DESPOT: Causally-Informed Online POMDP Planning for Robots in Confounded Environments

arXiv: https://arxiv.org/abs/2304.06848 · HTML: https://mlsanity.com/paper/2304.06848/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- Builds on 12 of its 33 references that are in the map.
- First posted on arXiv 13 Apr 2023.

## Builds on (most cited first, 12 of 12)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Pyro: Deep Universal Probabilistic Programming](https://mlsanity.com/paper/1810.09538/) (2018)
- [Black Box Variational Inference](https://mlsanity.com/paper/1401.0118/) (2013)
- [DESPOT: Online POMDP Planning with Regularization](https://mlsanity.com/paper/1609.03250/) (2016)
- [Shaking the foundations: delusions in sequence models for interaction and control](https://mlsanity.com/paper/2110.10819/) (2021)
- [Partially Observable Markov Decision Processes (POMDPs) and Robotics](https://mlsanity.com/paper/2107.07599/) (2021)
- [Causal Reinforcement Learning using Observational and Interventional Data](https://mlsanity.com/paper/2106.14421/) (2021)
- [Automated Variational Inference in Probabilistic Programming](https://mlsanity.com/paper/1301.1299/) (2013)
- [A Review of the Role of Causality in Developing Trustworthy AI Systems](https://mlsanity.com/paper/2302.06975/) (2023)
- [Why did I fail? A Causal-based Method to Find Explanations for Robot Failures](https://mlsanity.com/paper/2204.04483/) (2022)
- [POMDP-lite for Robust Robot Planning under Uncertainty](https://mlsanity.com/paper/1602.04875/) (2016)
- [A Causal-based Approach to Explain, Predict and Prevent Failures in Robotic Tasks](https://mlsanity.com/paper/2209.05255/) (2022)

## Built on by (most cited first, 12 of 12)

- [ROS-Causal: A ROS-based Causal Analysis Framework for Human-Robot Interaction Applications](https://mlsanity.com/paper/2402.16068/) (2024)
- [Towards Probabilistic Causal Discovery, Inference & Explanations for Autonomous Drones in Mine Surveying Tasks](https://mlsanity.com/paper/2308.10047/) (2023)
- [Experimental Evaluation of ROS-Causal in Real-World Human-Robot Spatial Interaction Scenarios](https://mlsanity.com/paper/2406.04955/) (2024)
- [Extending Structural Causal Models for Autonomous Vehicles to Simplify Temporal System Construction & Enable Dynamic Interactions Between Agents](https://mlsanity.com/paper/2406.01384/) (2024)
- [Causality-enhanced Decision-Making for Autonomous Mobile Robots in Dynamic Environments](https://mlsanity.com/paper/2504.11901/) (2025)
- [Learning Causal Structure Distributions for Robust Planning](https://mlsanity.com/paper/2508.06742/) (2025)
- [COBRA-PPM: A Causal Bayesian Reasoning Architecture Using Probabilistic Programming for Robot Manipulation Under Uncertainty](https://mlsanity.com/paper/2403.14488/) (2024)
- [Generating Causal Explanations of Vehicular Agent Behavioural Interactions with Learnt Reward Profiles](https://mlsanity.com/paper/2503.14557/) (2025)
- [HyPlan: Hybrid Learning-Assisted Planning Under Uncertainty for Safe Autonomous Driving](https://mlsanity.com/paper/2510.07210/) (2025)
- [Learning Causal States Under Partial Observability and Perturbation](https://mlsanity.com/paper/2512.00357/) (2025)
- [Planning under Distribution Shifts with Causal POMDPs](https://mlsanity.com/paper/2602.23545/) (2026)
- [Estimating the Causal Impact of Social Navigation Signals in Corridor Scenarios](https://mlsanity.com/paper/2610.16411/) (2026)

## Abstract (arXiv)

Robots operating in real-world environments must reason about possible outcomes of stochastic actions and make decisions based on partial observations of the true world state. A major challenge for making accurate and robust action predictions is the problem of confounding, which if left untreated can lead to prediction errors. The partially observable Markov decision process (POMDP) is a widely-used framework to model these stochastic and partially-observable decision-making problems. However, due to a lack of explicit causal semantics, POMDP planning methods are prone to confounding bias and thus in the presence of unobserved confounders may produce underperforming policies. This paper presents a novel causally-informed extension of "anytime regularized determinized sparse partially observable tree" (AR-DESPOT), a modern anytime online POMDP planner, using causal modelling and inference to eliminate errors caused by unmeasured confounder variables. We further propose a method to learn offline the partial parameterisation of the causal model for planning, from ground truth model data. We evaluate our methods on a toy problem with an unobserved confounder and show that the learned causal model is highly accurate, while our planning method is more robust to confounding and produces overall higher performing policies than AR-DESPOT.